bytedance/agentkit-samples is a collection of examples and tutorials for Volcengine AgentKit, an AI-agent development platform for building, deploying, and operating agent applications. Developers use the samples to learn agent creation, multi-agent collaboration, memory, retrieval, MCP integrations, media generation, customer service, and other workflows. The catalogue skills provide agent workflows based on these examples.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add bytedance/agentkit-samples --skill byted-sms-sendergit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bytedance/agentkit-samples/byted-sms-sender)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-sms-sender"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-sms-sender/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/byted-sms-sender"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/byted-sms-sender.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00189 | $0.01089 |
| Opus 5 | $0.00095 | $0.00544 |
| Sonnet 5 | $0.00038 | $0.00218 |
| Haiku 4.5 | $0.00019 | $0.00109 |
Grade A, and why
byted-sms-sender scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
火山引擎短信
始终通过 python3 -B <skill目录>/scripts/sms_cli.py 执行业务，不绕过脚本调用写
Action。默认客户不会使用终端：Agent 负责安装、登录、命令和清理，客户只操作浏览器
并确认业务写入。除非客户询问，不展示命令、JSON、CLI、Profile、HOME、AK/SK 或沙箱。
入口流程
- 首次调用或鉴权失败时读取 auth-setup.md，执行
auth-doctor并严格跟随唯一error.remediation；auth_ready后恢复原任务。 - 首次业务调用执行只读
list-message-groups。只有RE:0001才读取 service-onboarding.md；空列表和资源缺失不代表服务 未开通。 - 按任务读取下面最小参考集合，再执行 CLI。
按任务读取
- 所有任务先读公共 Action 配置与错误规则：actions.md。
- 资质、签名、模板申请读 application-contracts.md。
- 资质材料和本机表单再读
qualification-materials.md；展示方式由其中链接的
qualification-display.md决定。 - 单发、群发、回执和分析读 delivery-contracts.md。
- 需要完整编排顺序时读 workflows.md。
- 写操作授权、脱敏、重试和对账统一读 rules.md。
CLI 工作流
- 查询：
list-message-groups、message-group-detail、list-qualifications、list-signatures、list-templates。 - 资质：先尝试 MCP App 右侧面板；调用
open_qualification_application后紧接着调用ensure_qualification_application_visible。面板不可见时按 qualification-display.md 改用宿主内置浏览器， 宿主不支持时才使用系统浏览器。 - 申请：
*-preview→ 客户确认 →*-submit。 - 单发：
match-template→send-preview→ 客户授权 →send-submit→send-status。 - 群发：
batch-template-demo/batch-precheck→batch-create→batch-launch-preview→ 指定任务授权 →batch-launch-submit；管理使用batch-detail、batch-list、batch-cancel。 - 分析：
analytics；只有需要消息级证据时增加--include-logs。
不可变边界
- 鉴权只执行 remediation；同一时间一个登录会话。其他登录方式不索取登录入口链接，AK/SK
只在客户主动选择时提示一套
VOLCENGINE_*变量。 - 资质敏感材料只在本机向导填写。Agent 读取掩码后的
QUALIFICATION_EXCHANGE和QUALIFICATION_FAILURE排查，不要求客户复制字段或上传到对话。 - 申请、发送和任务启动都基于当前预览授权；字段变化后重新预览。
- 可能已发出的写请求不重试、不切换调用路径，返回
outcome_unknown并按契约对账。 - 创建或启动群发不代表送达；只有公开发送日志是消息级证据。
- 最终输出不包含完整个人信息、图片、文件地址、凭证、ticket、Authorization 或签名 URL 查询参数；保留公开 Request ID 和错误码，不推断内部原因。
What ships with it
30 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 354 B
- assets/qualification_mcp_app.html 7.4 KB
- assets/qualification_wizard_vendor/arco-icon.min.js.br 29 KB
- assets/qualification_wizard_vendor/arco.min.css.br 46 KB
- assets/qualification_wizard_vendor/arco.min.js.br 215 KB
- assets/qualification_wizard_vendor/react-dom.production.min.js 129 KB runs code
- assets/qualification_wizard_vendor/react.production.min.js 10 KB runs code
- assets/qualification_wizard_vendor/THIRD_PARTY_NOTICES.txt 2.8 KB
- assets/qualification_wizard.css 12 KB
- assets/qualification_wizard.html 1.3 KB
- assets/qualification_wizard.js 54 KB runs code
- assets/qualification_wizard.jsx 93 KB
- LICENSE 11 KB
- references/actions.md 4.3 KB
- references/application-contracts.md 4.8 KB
- references/auth-setup.md 3.6 KB
- references/delivery-contracts.md 4.4 KB
- references/qualification-display.md 2.1 KB
- references/qualification-materials.md 6.7 KB
- references/rules.md 2.1 KB
- references/service-onboarding.md 2.0 KB
- references/workflows.md 3.8 KB
- scripts/action_contracts.py 12 KB runs code
- scripts/analytics.py 19 KB runs code
- scripts/api_client.py 94 KB runs code
- scripts/qualification_display.py 2.2 KB runs code
- scripts/qualification_mcp_server.py 21 KB runs code
- scripts/qualification_upload.py 45 KB runs code
- scripts/qualification_wizard.py 66 KB runs code
- scripts/sms_cli.py 89 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 64 lines · 189 tokens per session scan A 1f61ab2e2d97
byted-sms-sender is a skill published in the GitHub repository bytedance/agentkit-samples (450 stars, last pushed 5d ago), licensed Apache-2.0. It adds 189 tokens to every session and 1,089 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
sn-image-imitate
An image tool that creates new content while following the visual style and layout of a single reference image.